高效擴散模型：從原理到實踐的全面調查

Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

October 15, 2024

作者: Zhiyuan Ma, Yuzhu Zhang, Guoli Jia, Liangliang Zhao, Yichao Ma, Mingjie Ma, Gaofeng Liu, Kaiyan Zhang, Jianjun Li, Bowen Zhou

cs.AI

摘要

作為近年來最受歡迎和尋求的生成模型之一，擴散模型引起了許多研究人員的興趣，並在各種生成任務中穩定地展現出優勢，例如圖像合成、視頻生成、分子設計、3D場景渲染和多模態生成，這些都依賴於它們密集的理論原則和可靠的應用實踐。這些最近在擴散模型上取得的顯著成功很大程度上來自於漸進式設計原則和高效的架構、訓練、推斷和部署方法。然而，迄今為止還沒有全面深入的回顧來總結這些原則和實踐，以幫助對擴散模型的快速理解和應用。在這份調查中，我們提供了一個新的以效率為導向的觀點，主要聚焦於架構設計、模型訓練、快速推斷和可靠部署中的深刻原則和高效實踐，以引導進一步的理論研究、算法遷移和模型應用，以應對新情境，同時以讀者友好的方式呈現。 https://github.com/ponyzym/Efficient-DMs-Survey

English

As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis, video generation, molecule design, 3D scene rendering and multimodal generation, relying on their dense theoretical principles and reliable application practices. The remarkable success of these recent efforts on diffusion models comes largely from progressive design principles and efficient architecture, training, inference, and deployment methodologies. However, there has not been a comprehensive and in-depth review to summarize these principles and practices to help the rapid understanding and application of diffusion models. In this survey, we provide a new efficiency-oriented perspective on these existing efforts, which mainly focuses on the profound principles and efficient practices in architecture designs, model training, fast inference and reliable deployment, to guide further theoretical research, algorithm migration and model application for new scenarios in a reader-friendly way. https://github.com/ponyzym/Efficient-DMs-Survey